ClarenceKe / TRCA-SSVEP

Task-related component analysis (TRCA)-based algorithm for detecting steady-state visual evoked potentials (SSVEPs) toward a high-speed brain-computer interface (BCI).

Overview

Task-related component analysis (TRCA)-based algorithm for detecting steady-state visual evoked potentials (SSVEPs) toward a high-speed brain-computer interface (BCI) [1].

Description

Scalp electroencephalogram (EEG) signals can be considered as instantanuous linear mixtures of activities from multiple cortical sources. In other words, the cortical source signals can be estimated/reconstructed from a weighted linear combination of multi-channel scalp EEG signals. The TRCA finds a optimal weight coefficients to maximize the reproducibility of time-locked activities across task trials, leading to significantly enhanced signal-to-noise ratio (SNR) of task-related EEG components.

The distribution includes:

• data/sample.mat : Sample data (See below)
• src/train_trca.m : Training classifier based on TRCA
• src/test_trca.m : Classifying SSVEPs using TRCA-based classifier
• src/test_fbcca.m : Classifying SSVEPs using FBCCA
• src/filterbank.m : Designing a filter bank
• src/itr.m : Calculating information transfer rate (ITR)
• tutorial/tutorial_trca : Tutorial of TRCA-based SSVEP detection
• tutorial/tutorial_fbcca : Tutorial of FBCCA-based SSVEP detection

Dataset (sample.mat)

A 40-target SSVEP dataset recorded from a single subject. The stimuli were generated by the joint frequency-phase modulation (JFPM) [2]

[# of targets, # of channels, # of sampling points, # of blocks] = size(eeg);

• Stimulus frequencies : 8.0 - 15.8 Hz with an interval of 0.2 Hz
• Stimulus phases : 0pi, 0.5pi, 1.0pi, and 1.5pi
• Number of channels : 9 (1: Pz, 2: PO5,3: PO3, 4: POz, 5: PO4, 6: PO6, 7: O1, 8: Oz, and 9: O2)
• Number of recording blocks : 6
• Length of an epoch : 5 s
• Sampling rate : 250 Hz

References

1. M. Nakanishi, Y. Wang, X. Chen, Y. -T. Wang, X. Gao, and T.-P. Jung, "Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis", IEEE Trans. Biomed. Eng, 65(1): 104-112, 2018. http://ieeexplore.ieee.org/document/7904641/
2. X. Chen, Y. Wang, M. Nakanishi, X. Gao, T. -P. Jung, S. Gao, "High-speed spelling with a non-invasive brain-computer interface", Proc. Natl. Acad. Sci. U.S.A, 112(44): E6058-E6067, 2015. http://www.pnas.org/content/early/2015/10/14/1508080112.abstract